Translate a document

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description discloses useful behaviors like saving next to the source, returning the path, and credit costs. However, it contradicts the input schema's wait_seconds parameter, which mentions returning a job ID. This creates ambiguity about whether the tool runs synchronously or asynchronously, a critical behavioral trait.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three sentences, each earning its place: purpose, supported formats, output/cost behavior. Front-loaded, scannable, and free of filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema and no annotations, the description must clarify return values and job behavior. The 'returns its path' statement conflicts with the job-id mention in wait_seconds, and the existence of sibling check_job implies asynchronous processing. Missing details on failure modes or polling make it incomplete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the description adds marginal value. It does add supported-formats context beyond the schema, but fails to reconcile the wait_seconds behavior described in the schema, leaving potential confusion.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool translates a document into another language while preserving layout, tables, images, and formulas. It also lists supported file formats, which distinctly separates it from sibling tools like condense_document or humanize_document.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides context by listing accepted formats and requires credit-cost agreement before use, implying when it should be used for document translation. However, it never explicitly mentions alternatives or when not to use this tool, leaving the choice versus sibling tools implicit.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.